Built so your credentials never touch the AI, every send waits for your approval, and your data never trains a model.
Reggie reads your pipeline and runs your outreach, so Revr is built to a higher bar than a normal CRM. Not a policy. The architecture.
Every outreach email and text Reggie writes lands in your review queue as a draft. You approve, edit, or skip it.
Here’s exactly what Revr touches, and what it never does.
The controls are real today; the paperwork is catching up. Here’s the status of each, no badge inflation.
Who touches your data, by name, and what you control.
Supabase (managed PostgreSQL) and Vercel, both US-hosted. Secrets live only in server-side environment variables. Never in client code or the repository.
Reggie runs on OpenAI and Anthropic. Named here, not “leading AI models.” Only the records a task needs are sent, under commercial APIs that do not train on what they receive.
Export everything to CSV any time. Disconnect any integration to delete its credentials immediately. Delete your account and every connected mailbox is cut off at once.
The full subprocessor list ships in our compliance pack, request it, a vendor security review, or a DPA at security@getrevr.com.
Asked by brokers, IT departments, and lawyers. Answered without the hedging.
Approving Revr for a Google Workspace or Microsoft 365 tenant? Every permission Revr requests, and how to approve it has the application IDs, the consent link, and exactly what reads a mailbox and when.
No. Every outreach email and text he drafts lands in your review queue, and the approval gate is enforced server-side. An already-sent draft can’t fire twice, and automations default to draft-for-review. Auto-send exists only where you deliberately turn it on, and you can turn it off any time.
We’ll walk them through the architecture, complete a vendor security review, and provide a DPA on request.
Contact us about security